Oracle® Retail Demand Forecasting Cloud Service Implementation Guide Release 19.0 for Windows F24923-16 |
|
![]() Previous |
![]() Next |
This appendix describes how RDF Cloud Service supports integration with Oracle Retail Advanced Science Engine (ORASE) and Oracle Retail Insights (RI).
RDF CS supports integration with ORASE to import the Demand Transference multiplier, import Size Profile Data, and export the forecast and promotion effects.
RDF CS can import the Demand Transference (DT) Multiplier from ORASE and use it to calculate the DT Effects if DT is enabled.
ORASE exports the DT multiplier file dtmul.csv.ovr
to the Cloud Share location compressed as the ORASE_WEEKLY_ extract.zip
file, together with the trigger file with the extension, .complete
.
The customer can schedule the Import RI/DT Measures OAT task to import the DT multiplier. This process also loads the dtmul
measure.
RDF CS can import the size profile generated by Size Profile Optimization (SPO) to spread the short lifecycle forecast from skup to sku level.
SPO exports the file spo_size_profile.csv
to the Cloud Share location compressed as the ORASE_WEEKLY_ extract.zip
file.
The customer can schedule the Online Administration Task Import Size Profile which extracts the required columns from the input file for the rows set as Y for column USED_BY_RDF. This process creates the file sizeprofile.csv.ovr
at sku/stor level and load the sizeprofile
measure.
RDF CS exports the forecast and promotion related data to RI. RI serves as a central port for the retailer for all the insights. Table E-1 describes the files exported by the Export RI Base Demand OAT task. Each file exported to RI has a corresponding control (.ctx
) file.
Table E-1 Files Exported by the Export RI Base Demand OAT Task
File # | Measure | Intersection | File Name | Control File |
---|---|---|---|---|
1 |
Baseline System Forecast |
sku/store/week |
W_RTL_PLANFC_PROD1_LC1_T1_FS.dat |
W_RTL_PLANFC_PROD1_LC1_T1_FS.dat.ctx |
Baseline Approved Forecast |
||||
Baseline Approved Cumulative Intervals |
||||
2 |
System Forecast |
sku/store/week |
W_RTL_PLANFC_PROD2_LC2_T2_FS.dat |
W_RTL_PLANFC_PROD2_LC2_T2_FS.dat.ctx |
Approved Forecast |
||||
Approved Forecast Cumulative Intervals |
||||
3 |
LLC Causal Variables |
lprm |
W_RTL_PLANFC_PARAM_DS.dat |
W_RTL_PLANFC_PARAM_DS.dat.ctx |
SLC Causal Variables |
sprm |
|||
4 |
LLC causal effects |
sku/stor/lprm |
W_RTL_PLANFC_PARAM_IT_LC_DS.dat |
W_RTL_PLANFC_PARAM_IT_LC_DS.dat.ctx |
SLC causal effects |
sku/stor/sprm |
|||
5 |
Baseline Approved Forecast |
sku/store/week |
W_RTL_PLANFC1_PROD1_LC1_T1_FS.dat |
W_RTL_PLANFC_PROD1_LC1_T1_FS.dat
2019-04-04;00:00:00|sku123456|stor104|1234.1234|1234.1234|22.33
W_RTL_PLANFC_PROD2_LC2_T2_FS.dat
2019-04-04;00:00:00|sku123456|stor104|1234.1234|1234.1234|22.33
W_RTL_PLANFC_PARAM_DS.dat
pvarlpr1 |boolean|linear
pvarlpr2|boolean|linear
pvarlpr3|real|exponential
pvarspr2|boolean|linear
pvarspr3|real|power
W_RTL_PLANFC_PARAM_IT_LC_DS.dat
sku123456|stor104|pvarlpr1|2.1
sku123456|stor104|pvarlpr2|2.5
sku123456|stor105|pvarlpr3|1.5
sku123456|stor106|pvarspr2|2.5
sku123456|stor107|pvarspr3|1.5